IIIT Hyderabad Publications |
|||||||||
|
Solving Multilabel MRFs using Incremental -Expansion on the GPUsAuthors: Vibhav Vineet,P J Narayanan Conference: ACCV 2009 (Asian Conference on Computer Vision 2009) Date: 2009-09-23 Report no: IIIT/TR/2009/230 AbstractMany vision problems map to the minimization of an energy function over a discrete MRF. Fast performance is needed if the energy minimization is one step in a control loop. In this paper, we present the incremental -expansion algorithm for high-performance multilabel MRF optimization on the GPU. Our algorithm utilizes the grid structure of the MRFs for good parallelism on the GPU.We improve the basic push-relabel implementation of graph cuts using the atomic operations of the GPU and by processing blocks stochastically. We also reuse the flow using reparametrization of the graph from cycle to cycle and iteration to iteration for fast performance. We show results on various vision problems on standard datasets. Our approach takes 950 milliseconds on the GPU for stereo correspondence on Tsukuba image with 16 labels compared to 5.4 seconds on the CPU. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |